Skip to content
Hallway
0:00 / 0:00

#aisafety#pascal'smugging#pascal'swager

Is AI Safety a Pascal's Mugging?

Robert Miles AI Safety

174K subscribers • 9 videos on Hallway

YouTube
  • Recommended by 3 people: 3 on Hacker News.
  • A classic. People kept recommending it from 2019 to 2026.
  • Presented by Robert Miles, AI safety communicator
  • May be out of date. Uploaded 7 years ago, in an area where tools change fast.
  • An opinion. It argues one side of a question engineers disagree on.

Beginner. No background in the topic needed.

388K views7 years ago3 recommendations

AI and machine learningAI safety and impactComputation and complexity

Robert Miles examines whether the case for AI safety relies on Pascal's mugging, arguing that AI risk does not depend on vanishingly small probabilities.

An event that's very unlikely is still worth thinking about, if the consequences are big enough. What's the limit though? Do we have to devote all of our resources to any outcome that might give infinite payoffs, even if it seems basically impossible? Does the case for AI Safety rely on this kind of Pascal's Wager argument? Watch this video to find out that the answer to these questions is 'No'. Correction: At the embedded video says 3^^^3 has 3.6 trillion digits, but that's actually only the size of 3^^4. 3^^^3 is enormously larger. The Alignment Newsletter Podcast: alignment-newsletter.libsyn.com/ RSS feed to put into apps: alignment-newsletter.libsyn(dot)com/rss With thanks to my excellent Patreon supporters: patreon.com/robertskmiles Jason Hise Jordan Medina Scott Worley JJ Hepboin Pedro A Ortega Said Polat Chris Canal Nicholas Kees Dupuis Jake Ehrlich Mark Hechim Kellen lask Francisco Tolmasky Michael Andregg James Richárd Nagyfi Phil Moyer Shevis Johnson Alec Johnson Lupuleasa Ionuț Clemens Arbesser Bryce Daifuku Allen Faure Simon Strandgaard Jonatan R Michael Greve Julius Brash Tom O'Connor Erik de Bruijn Robin Green Laura Olds Jon Halliday Paul Hobbs Jeroen De Dauw Tim Neilson Eric Scammell Igor Keller Ben Glanton Robert Sokolowski anul kumar sinha Jérôme Frossard Sean Gibat A.Russell Cooper Lawton Tyler Herrmann Tomas Sayder Ian Munro Jérôme Beaulieu Gladamas Sylvain Chevalier DGJono robertvanduursen Dmitri Afanasjev Brian Sandberg Marcel Ward Andrew Weir Ben Archer Scott McCarthy Kabs Tendayi Mawushe Jannik Olbrich Anne Kohlbrenner Jussi Männistö Mr Fantastic Wr4thon Archy de Berker Marc Pauly Joshua Pratt Andy Kobre Brian Gillespie Martin Wind Peggy Youell Poker Chen Kees Truls Paul Moffat Anders Öhrt Marco Tiraboschi Michael Kuhinica Fraser Cain Robin Scharf Oren Milman John Rees Seth Brothwell Brian Goodrich Kasper Schnack Michael Hunter Klemen Slavic Patrick Henderson Long Nguyen Melisa Kostrzewski Hendrik Daniel Munter Graham Henry Volotat Duncan Orr Bryan Egan James Fowkes Frame Problems Alan Bandurka Benjamin Hull Dave Tapley Tatiana Ponomareva Aleksi Maunu Michael Bates Simon Pilkington Dion Gerald Bridger Steven Cope Petr Smital Daniel Kokotajlo Joshua Davis Fionn Tyler LaBean Roger Yuchong Li Nathan Fish Diagon Giancarlo Pace patreon.com/robertskmiles

Why it's here

3 people recommend this

What people say. Recommended as a clear explanation of why AI safety concerns are not a Pascal's mugging or wager.

chiion Hacker News • Recommends

On “Sam Altman’s leap of faith”

Pascal's wager is actually logically flawed. If there are two separate AGI invented, and you could only have chosen to invest in one, then where's the infinite capture of value? See this video on a reasonable argument about this: link to this video
View on Hacker News

mpteston Hacker News • Recommends

On “OpenAI: Introducing SuperAlignment”

All of this discussion really makes me think of Robert Miles "Is ai safety a Pascal's mugging?" from 4 years(!) ago0. All of this discussion has been had by Ai safety researchers for years in my layman understanding... Maybe we can look to them for insight in to these questions? 0 link to this video
View on Hacker News

circuit10on Hacker News • Recommends

On “AI Causes Real Harm. Let’s Focus on That over the End-of-Humanity Hype”

The difference to Pascal’s wager is that with that the probability is vanishingly small, but given current progress the probability of AI causing an existential threat is actually quite high. You can’t just call anything that has very bad negative consequences Pascal’s wager Video about this: “Is AI Safety a Pascal’s Mugging?” link to this video
View on Hacker News

circuit10on Hacker News • Recommends

On “There is unequivocal evidence that Earth is warming”

Here’s a video called “Is AI safety a Pascal’s Mugging?”: link to this video From what I remember the main point of the video is that kind of situation happens when the probability involved is vanishingly small, and all the events you listed don’t have a vanishingly small probability, so they are not Pascal’s wager situations, just a normal rational safety concerns with particularly high consequences
View on Hacker News